drewcurran
commited on
Commit
•
27d08c3
1
Parent(s):
badaa15
Update README.md
Browse files
README.md
CHANGED
@@ -47,10 +47,25 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
-
|
|
51 |
-
|
52 |
-
|
|
53 |
-
| 2.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
|
55 |
|
56 |
### Framework versions
|
|
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
+
| Epoch | Step | Training Loss | Validation Loss | Bleu | Gen Len |
|
51 |
+
|:-----:|:-----:|:-------------:|:---------------:|:------:|:-------:|
|
52 |
+
| 1.0 | 4674 | 2.5538 | 2.2471 | 0.7389 | 18.1428 |
|
53 |
+
| 2.0 | 9348 | 2.4606 | 2.1615 | 0.8787 | 18.1105 |
|
54 |
+
| 3.0 | 14022 | 2.3877 | 2.0981 | 0.9630 | 18.0917 |
|
55 |
+
| 4.0 | 18696 | 2.3433 | 2.0538 | 1.0353 | 18.0855 |
|
56 |
+
| 5.0 | 23370 | 2.2914 | 2.0186 | 1.0902 | 18.0692 |
|
57 |
+
| 6.0 | 28044 | 2.2565 | 1.9939 | 1.1566 | 18.0789 |
|
58 |
+
| 7.0 | 32718 | 2.2539 | 1.9756 | 1.1935 | 18.0686 |
|
59 |
+
| 8.0 | 37392 | 2.2262 | 1.9628 | 1.1998 | 18.0759 |
|
60 |
+
| 9.0 | 42066 | 2.2097 | 1.9556 | 1.2209 | 18.0706 |
|
61 |
+
| 10.0 | 46740 | 2.2021 | 1.9529 | 1.2244 | 18.0659 |
|
62 |
+
|:-----:|:-----:|:-------------:|:---------------:|:------:|:-------:|
|
63 |
+
| 11.0 | 51414 | 2.1283 | 1.8698 | 1.3343 | 18.024 |
|
64 |
+
| 12.0 | 56088 | 2.1211 | 1.8516 | 1.3656 | 18.0194 |
|
65 |
+
| 13.0 | 60762 | 2.1063 | 1.8461 | 1.3828 | 18.0112 |
|
66 |
+
|:-----:|:-----:|:-------------:|:---------------:|:------:|:-------:|
|
67 |
+
| 14.0 | 65436 | 2.0545 | 1.8267 | 1.4183 | 18.0116 |
|
68 |
+
| 15.0 | 70110 | 2.0645 | 1.8172 | 1.4433 | 18.005 |
|
69 |
|
70 |
|
71 |
### Framework versions
|